BSc Computing Science (AI) student at the University of Alberta. Skilled in React, Node.js, Python, Docker, Kubernetes, and cloud-native systems.
Who I Am
I'm Pranav Namah Satish, a Computing Science (AI) student at the University of Alberta passionate about building intelligent and scalable systems at the intersection of software, cloud, and AI.
My experience spans full-stack development, AWS cloud services, containerization with Docker and Kubernetes, and AI integrations using modern foundation models. I'm particularly interested in AI engineering, MLOps, and building reliable systems that bridge machine learning and production infrastructure.
Beyond engineering, I mentor students, contribute to university communities, and continuously explore new technologies through research, projects, and hands-on learning.
Work History
Seeking Software Engineering, Cloud, or AI/ML roles. Available immediately.
What I Built
Full-stack, AI-powered, cloud-native systems built for real-world scale and impact.
Full-Stack Cloud Marketplace
Deployed marketplace on AWS EC2 using Nginx and PM2, achieving sub-2s page loads and 99.9% uptime. Integrated Gemini AI chatbot and Stripe payments through REST APIs. Implemented observability with Prometheus and Grafana, reducing incident detection time by 70%.
Serverless AI Culinary Assistant
Built a serverless architecture on AWS Amplify with AppSync GraphQL APIs, Cognito auth, and CI/CD pipelines via GitHub Actions. Integrated Amazon Bedrock (Claude 3 Sonnet) for real-time personalised recommendations. Monitored Core Web Vitals with Grafana Faro.
AI-Powered Book Discovery
Built a full-stack book discovery platform that transformed bookshelf images into personalized recommendations using computer vision, metadata enrichment, and AI-driven ranking workflows. Designed cloud-ready backend services optimised through caching, rate limiting, and containerised deployment.
AI Reliability Engineering Platform
Building an observability and debugging framework for AI pipelines that monitors LLM workflows, identifies failure points across RAG, prompting, and model inference stages, and performs automated root-cause analysis to accelerate troubleshooting and enhance production AI reliability.
AI Reliability & Cost Optimization Platform
Engineered an intelligent inference orchestration layer that optimizes LLM spending through complexity-aware routing, automated quality assurance, and self-improving feedback loops. Integrated multi-provider model management, real-time cost analytics, and escalation mechanisms to balance quality, latency, and operational efficiency at scale.
Explore the complete archive of my full-stack, AI, and cloud infrastructure projects.
Tech Stack
A curated toolkit spanning the full stack — from pixels to pipelines, cloud to AI.
Whether it's a full-stack role, cloud infrastructure, AI/ML, or DevOps — I'm ready to contribute from day one. My inbox is always open.